ForgeryGuard

Tue, 01 Sep 2026 00:00:00 +0000

Large language models will readily draft letters, certificates and official notices on request. That is useful, but it also makes forging institutional documents easier than it has ever been.

ForgeryGuard sits in front of the model and screens each request before it is answered. The aim is to block prompts that impersonate institutions or ask for fraudulent artifacts, while still allowing the legitimate document drafting that schools, offices and businesses depend on every day. The approach combines neural classification with symbolic reasoning, so that each decision can be explained rather than simply asserted.

Status: Research complete. Publication details will be added here once the paper is published.

Trust for AI Agents Offline

Tue, 01 Sep 2026 00:00:00 +0000

AI agents increasingly call tools, APIs and other agents on our behalf. Today’s identity and trust frameworks assume an agent can always reach a server to check credentials, an assumption that breaks in much of the world.

This project develops a lightweight attestation protocol that lets agents prove where a tool call came from and verify it locally, so trust holds even on intermittent networks. It targets the resource constrained deployments common across Africa and other emerging regions.

Full working title: Lightweight Attestation Based Provenance Verification for Autonomous AI Agent Tool Invocation: A Connectivity Resilient Trust Protocol for Resource Constrained AI Deployments.

Status: Ongoing research.

AI Security |

ForgeryGuard

Trust for AI Agents Offline